Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fen
    -0.06
    	answer
    -0.06
     програми
    -0.06
     Fen
    -0.06
    Entries
    -0.06
    alls
    -0.06
     dt
    -0.06
    ciler
    -0.06
    ItemType
    -0.06
     incentives
    -0.06
    POSITIVE LOGITS
     ACCEPT
    0.07
    :['
    0.07
    \brief
    0.07
     longing
    0.06
    NOWLED
    0.06
    >[↵
    0.06
     strtol
    0.06
    Materials
    0.06
     link
    0.06
     injector
    0.06
    Act Density 0.084%

    No Known Activations